jinaai/jina-embeddings-v4
Visual Document Retrieval
•
Updated
•
669
•
84
Ash C PRO
ashercn97
AI & ML interests
None yet
Recent Activity
liked
a model
2 days ago
jinaai/jina-embeddings-v4
upvoted
a
paper
3 days ago
jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual
Retrieval
liked
a model
5 days ago
katanemo/Arch-Agent-3B
Organizations
None yet
liked
a
model
2 days ago
upvoted
a
paper
3 days ago
liked
a
model
5 days ago
Performance diference versus unquantized 8b param version?
2
#1 opened 7 days ago
by
ashercn97
liked
a
model
6 days ago
updated
a
Space
8 days ago
published
a
Space
8 days ago
liked
a
model
11 days ago
liked
a
model
13 days ago
reacted to
their
post with 🚀
13 days ago
Post
1264
Awesome new project by
numind
Multi-modal structured data extraction. Give it a JSON schema, some sort of data (image, text) and optionally examples, and get the filled-in json schema as a result.
Kind of crazy.
THOUGHTS BELOW:
Its super fast and super effective. It is so practical.
Im getting basically instant results on an A100(40gb) with VLLM and the 4b size.
so exciting. AND COMMERCIAL FREIDNLYYYY
numind
Multi-modal structured data extraction. Give it a JSON schema, some sort of data (image, text) and optionally examples, and get the filled-in json schema as a result.
Kind of crazy.
THOUGHTS BELOW:
Its super fast and super effective. It is so practical.
Im getting basically instant results on an A100(40gb) with VLLM and the 4b size.
so exciting. AND COMMERCIAL FREIDNLYYYY
-
- 3 replies
A thank you and a question
5
#1 opened 13 days ago
by
ashercn97
liked
a
model
13 days ago
replied to
their
post
13 days ago
150 tk/sec with the 2b parameter model. SO AWESOME
replied to
their
post
13 days ago
omg sorry i forgot to link its their nuextract v2 check it out
posted
an
update
13 days ago
Post
1264
Awesome new project by
numind
Multi-modal structured data extraction. Give it a JSON schema, some sort of data (image, text) and optionally examples, and get the filled-in json schema as a result.
Kind of crazy.
THOUGHTS BELOW:
Its super fast and super effective. It is so practical.
Im getting basically instant results on an A100(40gb) with VLLM and the 4b size.
so exciting. AND COMMERCIAL FREIDNLYYYY
numind
Multi-modal structured data extraction. Give it a JSON schema, some sort of data (image, text) and optionally examples, and get the filled-in json schema as a result.
Kind of crazy.
THOUGHTS BELOW:
Its super fast and super effective. It is so practical.
Im getting basically instant results on an A100(40gb) with VLLM and the 4b size.
so exciting. AND COMMERCIAL FREIDNLYYYY
-
-
- 3 replies
liked
2
models
13 days ago
updated
a
model
14 days ago
published
2
models
15 days ago